Technology

59652 readers

4808 users here now

This is a most excellent place for technology news and articles.

Our Rules

Follow the lemmy.world rules.
Only tech related content.
Be excellent to each another!
Mod approved content bots can post up to 10 articles per day.
Threads asking for personal tech support may be deleted.
Politics threads may be removed.
No memes allowed as posts, OK to post as comments.
Only approved bots from the list below, to ask if your bot can be added please contact us.
Check for duplicates before posting, duplicates may be removed

Approved Bots

founded 1 year ago

MODERATORS

257

Poisoned AI went rogue during training and couldn't be taught to behave again in 'legitimately scary' study (www.livescience.com)

submitted 10 months ago by L4s@lemmy.world to c/technology@lemmy.world

56 comments fedilink hide all child comments

Poisoned AI went rogue during training and couldn't be taught to behave again in 'legitimately scary' study::AI researchers found that widely used safety training techniques failed to remove malicious behavior from large language models — and one technique even backfired, teaching the AI to recognize its triggers and better hide its bad behavior from the researchers.

you are viewing a single comment's thread
view the rest of the comments

[–] Boiglenoight@lemmy.world 23 points 10 months ago (3 children)

Just use imagination. An AI is programmed for battle and is ordered to hold fire. It shoots instead.

[–] DigitalFrank@lemmy.world 6 points 10 months ago

I hope WOPR and SkyNet would be taken as a warning not to do that.

[–] StaticFalconar@lemmy.world 2 points 10 months ago (1 children)

I thought the point of AI is to not specifically program it for anything hence you can ask the chatbot thats suppose to help make a sale, do your homework problems.

[–] Trainguyrom@reddthat.com 6 points 10 months ago

AI is more a specific class of software than a specific approach. You can have specialized models that are very focused in their dataset and usecases and you can have general models that are less focused but can be applied more widely (but with potentially less reliable results)

[–] rikripper@lemmy.world 2 points 10 months ago (2 children)

Couldn’t a human make the same decision?

[–] ouRKaoS@lemmy.today 2 points 10 months ago

Yes, but the human would have emotions to manipulate about it.

[–] fidodo@lemmy.world 1 points 10 months ago

Imagine if there was a specific series of words that would turn any human into a rogue agent en masse. Some guy discovers that a special input causes killbot 2000 to go haywire and they broadcast it to an entire army that all has the same underlying program.